SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models Paper • 2503.07605 • Published 24 days ago • 65
LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning Paper • 2312.03849 • Published Dec 6, 2023 • 7
HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces Paper • 2312.03160 • Published Dec 5, 2023 • 7
Self-conditioned Image Generation via Generating Representations Paper • 2312.03701 • Published Dec 6, 2023 • 9
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions Paper • 2312.03611 • Published Dec 6, 2023 • 9
MagicStick: Controllable Video Editing via Control Handle Transformations Paper • 2312.03047 • Published Dec 5, 2023 • 11
HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting Paper • 2312.03461 • Published Dec 6, 2023 • 17
Beyond Surface: Probing LLaMA Across Scales and Layers Paper • 2312.04333 • Published Dec 7, 2023 • 20
Chain of Code: Reasoning with a Language Model-Augmented Code Emulator Paper • 2312.04474 • Published Dec 7, 2023 • 33
Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians Paper • 2312.03029 • Published Dec 5, 2023 • 26
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation Paper • 2312.03641 • Published Dec 6, 2023 • 22
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want Paper • 2312.03818 • Published Dec 6, 2023 • 34
Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis Paper • 2312.03491 • Published Dec 6, 2023 • 35
Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models Paper • 2312.03632 • Published Dec 6, 2023 • 7
Alchemist: Parametric Control of Material Properties with Diffusion Models Paper • 2312.02970 • Published Dec 5, 2023 • 10